Arnold Schwaighofer 11eb51e239 LoopVectorize: Vectorize all accesses in address space zero with unit stride ...

We can vectorize them because in the case where we wrap in the address space the
unvectorized code would have had to access a pointer value of zero which is
undefined behavior in address space zero according to the LLVM IR semantics.
(Thank you Duncan, for pointing this out to me).

Fixes PR16592.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186088 91177308-0d34-0410-b5e6-96231b3b80d8

2013-07-11 15:21:55 +00:00

..

ADCE

…

ArgumentPromotion

…

BBVectorize

…

BlockPlacement

…

BranchFolding

…

CodeExtractor

…

CodeGenPrepare

…

ConstantMerge

…

ConstProp

…

CorrelatedValuePropagation

…

DeadArgElim

DeadArgumentElimination: keep return value on functions that have a live argument with the 'returned' attribute (rather than generate invalid IR); however, if both can be eliminated, both will be

2013-06-30 20:26:21 +00:00

DeadStoreElimination

…

DebugIR

Adding tests for DebugIR pass

2013-06-28 20:37:20 +00:00

EarlyCSE

…

FunctionAttrs

Extend 'readonly' and 'readnone' to work on function arguments as well as

2013-07-06 00:29:58 +00:00

GCOVProfiling

…

GlobalDCE

…

GlobalOpt

Always remove an alias when we rename the target.

2013-06-12 16:45:47 +00:00

GVN

Eliminate trivial redundant loads across nocapture+readonly calls to uncaptured

2013-07-07 10:15:16 +00:00

IndVarSimplify

IndVarSimplify: check if loop invariant expansion can trap

2013-06-04 17:51:58 +00:00

Inline

…

InstCombine

InstSimplify: X >> X -> 0

2013-07-09 22:01:22 +00:00

InstSimplify

InstSimplify: X >> X -> 0

2013-07-09 22:01:22 +00:00

Internalize

…

IPConstantProp

…

JumpThreading

…

LCSSA

…

LICM

…

LoopDeletion

…

LoopIdiom

…

LoopRotate

…

LoopSimplify

…

LoopStrengthReduce

LSR: Fix the parameters used to compute the scaling factor cost.

2013-06-19 19:59:41 +00:00

LoopUnroll

Prevent loop-unroll from making assumptions about undefined behavior.

2013-05-31 23:34:46 +00:00

LoopUnswitch

…

LoopVectorize

LoopVectorize: Vectorize all accesses in address space zero with unit stride

2013-07-11 15:21:55 +00:00

LowerAtomic

…

LowerExpectIntrinsic

…

LowerInvoke

…

LowerSwitch

…

Mem2Reg

…

MemCpyOpt

Fix a potential bug in r183584.

2013-06-08 04:56:05 +00:00

MergeFunc

…

MetaRenamer

…

ObjCARC

[objc-arc] Committed test for r185770 as per dblaikie's suggestion.

2013-07-08 02:13:47 +00:00

PhaseOrdering

…

PruneEH

…

Reassociate

…

Reg2Mem

…

ScalarRepl

Fix SROA to avoid unnecessary scalar conversions for 1-element vectors.

2013-06-25 19:09:50 +00:00

SCCP

…

SimplifyCFG

TryToSimplifyUncondBranchFromEmptyBlock was checking that any common

2013-07-11 08:28:20 +00:00

Sink

…

SLPVectorizer

Consolidate more lit tests.

2013-07-11 05:15:11 +00:00

SROA

…

StripSymbols

…

StructurizeCFG

Move StructurizeCFG out of R600 to generic Transforms.

2013-06-19 20:18:24 +00:00

TailCallElim

Teach TailRecursionElimination to handle certain cases of nocapture escaping allocas.

2013-07-11 04:40:01 +00:00

TailDup

…